2. Data Preparation
2.1 Install and launch R packages
The project uses p_load() of pacman package to check if the R packages are installed in the computer.
The following code chunk is used to install and launch the R packages.
Show code
pacman:: p_load (tidyverse, kableExtra,
leaflet, rmarkdown, knitr,
highcharter, # timeseries highchart
viridis, ggthemes,
ggplot2, tidyr, dplyr, viridisLite, RColorBrewer,
calendR, # calendar
lubridate, # convert date from char to date format
wordcloud, tidytext, # word cloud
ggforce, # boxplot
countrycode, sf, spdep, tmap, leaflet, # geospatial
tm, plotly)
2.2 Import Data
Show code
data <- read.csv ("data/1900-01-01-2024-02-26-Southeast_Asia-Myanmar.csv" )
2.3 Overview of the data
Dataset Structure
Use str() to check the structure of the data.
'data.frame': 55574 obs. of 35 variables:
$ event_id_cnty : chr "MMR56099" "MMR56222" "MMR56370" "MMR56376" ...
$ event_date : chr "31-Dec-23" "31-Dec-23" "31-Dec-23" "31-Dec-23" ...
$ year : int 2023 2023 2023 2023 2023 2023 2023 2023 2023 2023 ...
$ time_precision : int 1 1 1 1 1 1 1 1 1 1 ...
$ disorder_type : chr "Political violence" "Political violence" "Political violence" "Demonstrations" ...
$ event_type : chr "Explosions/Remote violence" "Explosions/Remote violence" "Battles" "Protests" ...
$ sub_event_type : chr "Shelling/artillery/missile attack" "Shelling/artillery/missile attack" "Armed clash" "Peaceful protest" ...
$ actor1 : chr "Military Forces of Myanmar (2021-)" "Military Forces of Myanmar (2021-)" "Phoenix DF: Phoenix Defense Force (Nattalin)" "Protesters (Myanmar)" ...
$ assoc_actor_1 : chr "" "" "" "" ...
$ inter1 : int 1 1 3 6 1 1 3 1 2 1 ...
$ actor2 : chr "" "Civilians (Myanmar)" "Military Forces of Myanmar (2021-)" "" ...
$ assoc_actor_2 : chr "" "" "" "" ...
$ inter2 : int 0 7 1 0 7 0 1 0 1 7 ...
$ interaction : int 10 17 13 60 17 10 13 10 12 17 ...
$ civilian_targeting: chr "" "Civilian targeting" "" "" ...
$ iso : int 104 104 104 104 104 104 104 104 104 104 ...
$ region : chr "Southeast Asia" "Southeast Asia" "Southeast Asia" "Southeast Asia" ...
$ country : chr "Myanmar" "Myanmar" "Myanmar" "Myanmar" ...
$ admin1 : chr "Mon" "Rakhine" "Bago-West" "Sagaing" ...
$ admin2 : chr "Mawlamyine" "Maungdaw" "Thayarwady" "Yinmarbin" ...
$ admin3 : chr "Ye" "Maungdaw" "Nattalin" "Salingyi" ...
$ location : chr "Aing Shey" "Kaing Gyi (NaTaLa)" "Kyauk Pyoke" "Let Pa Taung" ...
$ latitude : num 15.3 20.7 18.6 22.1 18.6 ...
$ longitude : num 98 92.4 95.8 95.1 95.8 ...
$ geo_precision : int 1 2 2 2 1 1 1 2 2 1 ...
$ source : chr "Democratic Voice of Burma" "Development Media Group; Narinjara News" "Khit Thit Media; Myanmar Pressphoto Agency" "Myanmar Labour News" ...
$ source_scale : chr "National" "Subnational" "National" "National" ...
$ notes : chr "On 31 December 2023, in Aing Shey village (Ye township, Mawlamyine district, Mon state), following a clash betw"| __truncated__ "On 31 December 2023, in Kaing Gyi (Mro) village (coded as Kaing Gyi (NaTaLa)) (Maungdaw township, Maungdaw dist"| __truncated__ "On 31 December 2023, near Kyauk Pyoke village (Nattalin township, Thayarwady district, Bago-West region), the P"| __truncated__ "On 31 December 2023, in the Let Pa Taung area of Salingyi township (Yinmarbin district, Sagaing region), protes"| __truncated__ ...
$ fatalities : int 0 0 4 0 0 0 3 0 0 0 ...
$ tags : chr "" "" "" "crowd size=no report" ...
$ timestamp : int 1704831212 1704831213 1704831214 1704831214 1704831214 1704831216 1704831216 1704831216 1704831216 1704831216 ...
$ population_1km : int NA NA NA 749 NA 178 6634 671 687 35292 ...
$ population_2km : int NA NA NA 521 NA 135 19078 2197 654 85732 ...
$ population_5km : int 3081 NA NA 1358 NA NA 34396 3144 656 169473 ...
$ population_best : int 3081 NA NA 749 NA NA 34396 3144 656 85732 ...
Use colSums to check for missing values
missing_values <- colSums (is.na (data))
missing_values %>% kable ()
event_id_cnty
0
event_date
0
year
0
time_precision
0
disorder_type
0
event_type
0
sub_event_type
0
actor1
0
assoc_actor_1
0
inter1
0
actor2
0
assoc_actor_2
0
inter2
0
interaction
0
civilian_targeting
0
iso
0
region
0
country
0
admin1
0
admin2
0
admin3
0
location
0
latitude
0
longitude
0
geo_precision
0
source
0
source_scale
0
notes
0
fatalities
0
tags
0
timestamp
0
population_1km
9827
population_2km
9996
population_5km
10318
population_best
20848
Use duplicate() to check for duplicates:
3. Data Wrangling
The flowchart diagram below provides an overview of the key variables used in this project.
Use xxx convert to date format:
data$ event_date <- dmy (data$ event_date)
4. Initial Exploratory Data Analysis
4.1 Descriptive Statistics
Before proceeding with data visualisation, it is essential to be able to navigate the dataset of 55,574 observations with ease. This segment will help users identify or navigate through the dataset observations instead of scrolling through each observation one-by-one. The interactive datatable is created using DT package.
Display number of observations by selecting the dropdown (5, 10, 25, 50, 100 entries). This ensure that the observations will not span across the entire webpage.
View other pages of observations with “previous” or “next” button.
Search specific observations with the search bar for the occurence of a string/ numercial value in any column of an observation
Filter observations with the filter bar directly below column headers.
Column visibility allows user to select the columns that they are interested to view and hide the rest
Show code
DT:: datatable (
data,
class = "compact" ,
filter = "top" ,
extensions = c ("Buttons" ),
options = list (
pageLength = 5 ,
columnDefs = list (
list (targets = c (1 : 27 , 29 : 31 ), className = "dt-center" ), # text align center
list (targets = c (28 ), visible = FALSE )
),
buttons = list (
list (extend = "colvis" , columns = c (1 : 31 ))
),
dom = "Bpiltf"
),
caption = "Table 1:"
)